[1]王静,刘建云,韩彦岭,等.基于实例分割和显著性计算的人工视觉多目标优化处理[J].中国医学物理学杂志,2023,40(3):320-327.[doi:DOI:10.3969/j.issn.1005-202X.2023.03.010]
　WANG Jing,LIU Jianyun,et al.Multi-object optimization approach for artificial vision based on instance segmentation and saliency detection[J].Chinese Journal of Medical Physics,2023,40(3):320-327.[doi:DOI:10.3969/j.issn.1005-202X.2023.03.010]
点击复制

基于实例分割和显著性计算的人工视觉多目标优化处理()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
40卷
期数:
2023年第3期
页码:
320-327
栏目:
医学影像物理
出版日期:
2023-03-29

文章信息/Info

Title:
Multi-object optimization approach for artificial vision based on instance segmentation and saliency detection
文章编号:
1005-202X（2023）03-0320-08
作者:
王静1; 2; 刘建云1; 韩彦岭1; 周汝雁1; 沈晓晶1
1.上海海洋大学信息学院， 上海 201306； 2.农业部渔业信息重点实验室， 上海 201306
Author(s):
WANG Jing1;  2;  LIU Jianyun1;  HAN Yanling1;  ZHOU Ruyan1;  SHEN Xiaojing1
1. College of Information Technology, Shanghai Ocean University, Shanghai 201306, China 2. Key Laboratory of Fisheries Information, Ministry of Agriculture, Shanghai 201306, China
关键词:
视网膜假体; 多物体识别; Swin-Transformer; 层级优化表达
Keywords:
Keywords: retinal prosthesis multi-object recognition Swin-Transformer hierarchical optimization expression
分类号:
R318
DOI:
DOI:10.3969/j.issn.1005-202X.2023.03.010
文献标志码:
A
摘要:
通过实例分割Swin-Transformer提取分割所有前景对象，融合亮度、大小和位置图像显著性特征，提出模拟人类视觉注意机制的多特征融合注意力层级计算模型，为不同级别的前景物体采用适合的光幻视分辨率和亮度表达，实现不同的刺激编码策略进行层级优化处理。通过人工假体视觉的仿真试验表明，在所提出的多目标层级优化表达策略下，试验被试完成多目标识别的准确率、识别时间表现具有一定的显著提升。利用深度学习实例分割技术，层级化光幻视编码以仿生人类视觉选择性注意，达到增强假体植入者在复杂场景下的多物体感知，为视觉假体图像信息编码和优化处理研究的发展与应用提供参考。
Abstract:
Abstract: All foreground objects are extracted and segmented through instance segmentation using Swin-Transformer, and the image saliency features of luminance, size and location are combined to construct a multi-feature fusion attention hierarchical computational model for simulating human visual attention mechanism. The suitable phosphene resolution and luminance are adopted for foreground objects of different importance levels to realize the hierarchical optimization using different stimulus coding strategies. The simulation experiments of artificial prosthesis vision show that the experimental subjects will achieve higher recognition accuracy and take less time to complete multi-object recognition when they adopt the proposed multi-target hierarchical optimization approach. Instance segmentation technique is used to cascade the phosphene coding for mimicking human visual selective attention, thereby enhancing the multi-object perception in complex scenes for visual prosthesis. The study provides a reference for the development and application of image information coding and optimization strategies for visual prosthesis.

相似文献/References:

[1]王静,张羽婷,张云,等.基于图像显著性的人工视觉图像处理策略[J].中国医学物理学杂志,2019,36(11):1277.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.007]
　WANG Jing,ZHANG Yuting,et al.Image processing strategy based on saliency detection for artificial vision[J].Chinese Journal of Medical Physics,2019,36(3):1277.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.007]

备注/Memo

备注/Memo:
【收稿日期】2022-09-29 【基金项目】国家自然科学基金（61806123，41871325）；国家重点研发计划（2019YFD0900805）；上海市青年科技英才扬帆计划（16YF1415700） 【作者简介】王静，副教授，主要研究方向：计算机视觉理论及应用、医学图像处理，E-mail: wangjing@shou.edu.cn 【通信作者】沈晓晶，副教授，主要研究方向：图像处理、计算机视觉，E-mail: xjshen@shou.edu.cn
更新日期/Last Update: 2023-03-29